© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8226
    Prev
    Next
    INDEX
    Explanations

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¸ĥæĭī
    -0.28
    -brand
    -0.26
     miá»ģn
    -0.25
    Insets
    -0.24
    <br
    -0.24
    ä¸Ńå¼ı
    -0.24
     cra
    -0.24
    é¢ĦåĪ¶
    -0.24
    豨
    -0.24
     Bra
    -0.24
    POSITIVE LOGITS
    à¸Ħว
    0.31
     shaken
    0.28
    ä½ķ
    0.27
    auc
    0.26
    urers
    0.25
    quier
    0.25
     touched
    0.25
     bá»ģ
    0.25
     Layer
    0.24
    volent
    0.24
    Activations Density 0.009%

    No Known Activations